Dynamic Mortality Risk Predictions in Pediatric Critical Care Using Recurrent Neural Networks
This work addresses mortality risk prediction in pediatric critical care, offering a dynamic and more accurate tool for clinicians, though it is incremental as it builds on existing RNN approaches applied to medical data.
The authors tackled predicting in-ICU mortality for pediatric patients by developing a recurrent neural network that processes sequential medical data, achieving significant improvements over existing clinical scores and static machine learning methods.
Viewing the trajectory of a patient as a dynamical system, a recurrent neural network was developed to learn the course of patient encounters in the Pediatric Intensive Care Unit (PICU) of a major tertiary care center. Data extracted from Electronic Medical Records (EMR) of about 12000 patients who were admitted to the PICU over a period of more than 10 years were leveraged. The RNN model ingests a sequence of measurements which include physiologic observations, laboratory results, administered drugs and interventions, and generates temporally dynamic predictions for in-ICU mortality at user-specified times. The RNN's ICU mortality predictions offer significant improvements over those from two clinically-used scores and static machine learning algorithms.